NEW: Universal PDF support!⚡️📄 OpenRouter now supports PDF processing for every LLM, including PDFs with images. Multi-model demo & details below:

🎯 Highlights: • Universal: Works with ALL models • Native PDF support for Gemini, Anthropic, OpenAI • Multimodal magic: PDFs’ images sent directly to models • Combine w/ web search for real-time context, or Auto Router if you're not sure which model to use (see below)

🔧 Two PDF engines available: 1. `mistral-ocr` (default): OCR support, extracts text + images ($2/1000 pages) 2. `pdf-text`: Free, text-only extraction (no images or OCR)

💡 Use via our API or right from the OpenRouter Chatroom, allowing multiple models to simultaneously synthesize multiple PDFs, instantly. Here's the Auto Router choosing the right model for you:

📖 Get started: Full docs & examples → Analyze PDFs with every model today, all in one place.

INTRODUCING: Agentic Security - LLM Security Scanner! 🔍 🔑 Features: Scans for prompt injections, jailbreaking & more. Provides detailed reports & options to customize attack rules. 🔗access the GitHub Link ↓

hello mr @charliebholtz when support in chorus

so glad i switched to openrouter, i'm loving it so far.

Why don’t you add Mistral’s OCR model as well?

The documentation shows a plain Typescript fetch example, in contrast with other examples in the docs which use the openai sdk. Why the difference?

Great!